{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U6QPAJCP6XFLKOD6WKE3QDUNLF","short_pith_number":"pith:U6QPAJCP","canonical_record":{"source":{"id":"2505.02579","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T11:30:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4bdbb465c58a0a54f4feae6ddd51adce9e50ef2127c64c0b81ac4429f0185fb6","abstract_canon_sha256":"9cbdadf985d03927774ea324c9b394ca63b621d5b364578bcdc8b01839f1b582"},"schema_version":"1.0"},"canonical_sha256":"a7a0f0244ff5cab5387eb289b80e8d5963ee326cdeea4f114f9629166c18d994","source":{"kind":"arxiv","id":"2505.02579","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02579","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02579v3","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02579","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"U6QPAJCP6XFL","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"U6QPAJCP6XFLKOD6","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"U6QPAJCP","created_at":"2026-07-05T11:34:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U6QPAJCP6XFLKOD6WKE3QDUNLF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02579","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T11:30:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4bdbb465c58a0a54f4feae6ddd51adce9e50ef2127c64c0b81ac4429f0185fb6","abstract_canon_sha256":"9cbdadf985d03927774ea324c9b394ca63b621d5b364578bcdc8b01839f1b582"},"schema_version":"1.0"},"canonical_sha256":"a7a0f0244ff5cab5387eb289b80e8d5963ee326cdeea4f114f9629166c18d994","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:07.928722Z","signature_b64":"J/sFYOAtD09wswo3vasBkuJSKJQ7YAHcERBTCkRUELFevGwd7o0Rj7uo5xRlSs1wU44+wnJQW43b7c3roCoOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a0f0244ff5cab5387eb289b80e8d5963ee326cdeea4f114f9629166c18d994","last_reissued_at":"2026-07-05T11:34:07.928262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:07.928262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02579","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USpE/9oCEUzFeZFeMkrd0no/Snc3uVuHbci+DCYYaYrk5YUCqkWpXmDAOoU0wSHJ8JStj+EmU78SivvbS2jSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:45:38.567334Z"},"content_sha256":"ec5e646b9ec08a555f7ae526c7df87316c957f1b0bd1ae383699638a942c4f03","schema_version":"1.0","event_id":"sha256:ec5e646b9ec08a555f7ae526c7df87316c957f1b0bd1ae383699638a942c4f03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U6QPAJCP6XFLKOD6WKE3QDUNLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cong Yang, Lingxiao Kong, Oya Deniz Beyan, Susanne Neufang, Zeyd Boukhers","submitted_at":"2025-05-05T11:30:46Z","abstract_excerpt":"Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training efficiency, poor scalability, and limited explainability. Leveraging ensemble learning principles, we introduce an Ensemble Multi-Objective RL (EMORL) framework that fine-tunes multiple models with individual objectives while optimizing their aggregation after the fine-tuning to improve efficiency and flexibility. Our method is the first to aggregate the hidden stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02579","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.02579/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Do7fAkNS1CZ6owro8og0OzpYzNYCOmzTw0ufGXdt4kLsbhEqFYFaEG+lHhkGcDGT71FlenDni75L/X+jlVn8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:45:38.567711Z"},"content_sha256":"5d02366bbba058699a5567d57182478c9e0faa09a1c768577683418f04c4bd44","schema_version":"1.0","event_id":"sha256:5d02366bbba058699a5567d57182478c9e0faa09a1c768577683418f04c4bd44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF/bundle.json","state_url":"https://pith.science/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T05:45:38Z","links":{"resolver":"https://pith.science/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF","bundle":"https://pith.science/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF/bundle.json","state":"https://pith.science/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6QPAJCP6XFLKOD6WKE3QDUNLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U6QPAJCP6XFLKOD6WKE3QDUNLF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9cbdadf985d03927774ea324c9b394ca63b621d5b364578bcdc8b01839f1b582","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T11:30:46Z","title_canon_sha256":"4bdbb465c58a0a54f4feae6ddd51adce9e50ef2127c64c0b81ac4429f0185fb6"},"schema_version":"1.0","source":{"id":"2505.02579","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02579","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02579v3","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02579","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"U6QPAJCP6XFL","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"U6QPAJCP6XFLKOD6","created_at":"2026-07-05T11:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"U6QPAJCP","created_at":"2026-07-05T11:34:07Z"}],"graph_snapshots":[{"event_id":"sha256:5d02366bbba058699a5567d57182478c9e0faa09a1c768577683418f04c4bd44","target":"graph","created_at":"2026-07-05T11:34:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.02579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training efficiency, poor scalability, and limited explainability. Leveraging ensemble learning principles, we introduce an Ensemble Multi-Objective RL (EMORL) framework that fine-tunes multiple models with individual objectives while optimizing their aggregation after the fine-tuning to improve efficiency and flexibility. Our method is the first to aggregate the hidden stat","authors_text":"Cong Yang, Lingxiao Kong, Oya Deniz Beyan, Susanne Neufang, Zeyd Boukhers","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T11:30:46Z","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02579","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ec5e646b9ec08a555f7ae526c7df87316c957f1b0bd1ae383699638a942c4f03","target":"record","created_at":"2026-07-05T11:34:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9cbdadf985d03927774ea324c9b394ca63b621d5b364578bcdc8b01839f1b582","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T11:30:46Z","title_canon_sha256":"4bdbb465c58a0a54f4feae6ddd51adce9e50ef2127c64c0b81ac4429f0185fb6"},"schema_version":"1.0","source":{"id":"2505.02579","kind":"arxiv","version":3}},"canonical_sha256":"a7a0f0244ff5cab5387eb289b80e8d5963ee326cdeea4f114f9629166c18d994","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7a0f0244ff5cab5387eb289b80e8d5963ee326cdeea4f114f9629166c18d994","first_computed_at":"2026-07-05T11:34:07.928262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:07.928262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J/sFYOAtD09wswo3vasBkuJSKJQ7YAHcERBTCkRUELFevGwd7o0Rj7uo5xRlSs1wU44+wnJQW43b7c3roCoOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:07.928722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02579","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec5e646b9ec08a555f7ae526c7df87316c957f1b0bd1ae383699638a942c4f03","sha256:5d02366bbba058699a5567d57182478c9e0faa09a1c768577683418f04c4bd44"],"state_sha256":"ac56518a5046a4fe2a730c0c9d1ae738f762373f7a12c4f7a4d118b3c091d0dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APH+vC5s4OjLiEmGjZK0WXtYlwSm6LrPmJhmLnisVEqLyhF1h3BpRtZwZ0rqNv0R6l1uanuEPkH/qvf+94ijBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T05:45:38.569718Z","bundle_sha256":"51ca956ca7d86b8d512c61163c613c7ef26fe3ecc95f5cfe833a48deb24b577e"}}